Sync 'ds/multi-pack-index' to v2.19.0-rc0

* ds/multi-pack-index: (23 commits)
  midx: clear midx on repack
  packfile: skip loading index if in multi-pack-index
  midx: prevent duplicate packfile loads
  midx: use midx in approximate_object_count
  midx: use existing midx when writing new one
  midx: use midx in abbreviation calculations
  midx: read objects from multi-pack-index
  config: create core.multiPackIndex setting
  midx: write object offsets
  midx: write object id fanout chunk
  midx: write object ids in a chunk
  midx: sort and deduplicate objects from packfiles
  midx: read pack names into array
  multi-pack-index: write pack names in chunk
  multi-pack-index: read packfile list
  packfile: generalize pack directory list
  t5319: expand test data
  multi-pack-index: load into memory
  midx: write header information to lockfile
  multi-pack-index: add 'write' verb
  ...

4 files changed, 232 insertions, 0 deletions

diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c
new file mode 100644
index 0000000000..8e19972e89
--- /dev/null
+++ b/t/helper/test-read-midx.c
@@ -0,0 +1,51 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "midx.h"
+#include "repository.h"
+#include "object-store.h"
+
+static int read_midx_file(const char *object_dir)
+{
+	uint32_t i;
+	struct multi_pack_index *m = load_multi_pack_index(object_dir);
+
+	if (!m)
+		return 1;
+
+	printf("header: %08x %d %d %d\n",
+	       m->signature,
+	       m->version,
+	       m->num_chunks,
+	       m->num_packs);
+
+	printf("chunks:");
+
+	if (m->chunk_pack_names)
+		printf(" pack-names");
+	if (m->chunk_oid_fanout)
+		printf(" oid-fanout");
+	if (m->chunk_oid_lookup)
+		printf(" oid-lookup");
+	if (m->chunk_object_offsets)
+		printf(" object-offsets");
+	if (m->chunk_large_offsets)
+		printf(" large-offsets");
+
+	printf("\nnum_objects: %d\n", m->num_objects);
+
+	printf("packs:\n");
+	for (i = 0; i < m->num_packs; i++)
+		printf("%s\n", m->pack_names[i]);
+
+	printf("object-dir: %s\n", m->object_dir);
+
+	return 0;
+}
+
+int cmd__read_midx(int argc, const char **argv)
+{
+	if (argc != 2)
+		usage("read-midx <object-dir>");
+
+	return read_midx_file(argv[1]);
+}
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index 0edafcfd65..3276701710 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -28,6 +28,7 @@ static struct test_cmd cmds[] = {
 	{ "path-utils", cmd__path_utils },
 	{ "prio-queue", cmd__prio_queue },
 	{ "read-cache", cmd__read_cache },
+	{ "read-midx", cmd__read_midx },
 	{ "ref-store", cmd__ref_store },
 	{ "regex", cmd__regex },
 	{ "repository", cmd__repository },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index e926c416ea..70fc0285e8 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -22,6 +22,7 @@ int cmd__online_cpus(int argc, const char **argv);
 int cmd__path_utils(int argc, const char **argv);
 int cmd__prio_queue(int argc, const char **argv);
 int cmd__read_cache(int argc, const char **argv);
+int cmd__read_midx(int argc, const char **argv);
 int cmd__ref_store(int argc, const char **argv);
 int cmd__regex(int argc, const char **argv);
 int cmd__repository(int argc, const char **argv);
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
new file mode 100755
index 0000000000..ae1d5d4592
--- /dev/null
+++ b/t/t5319-multi-pack-index.sh
@@ -0,0 +1,179 @@
+#!/bin/sh
+
+test_description='multi-pack-indexes'
+. ./test-lib.sh
+
+objdir=.git/objects
+
+midx_read_expect () {
+	NUM_PACKS=$1
+	NUM_OBJECTS=$2
+	NUM_CHUNKS=$3
+	OBJECT_DIR=$4
+	EXTRA_CHUNKS="$5"
+	{
+		cat <<-EOF &&
+		header: 4d494458 1 $NUM_CHUNKS $NUM_PACKS
+		chunks: pack-names oid-fanout oid-lookup object-offsets$EXTRA_CHUNKS
+		num_objects: $NUM_OBJECTS
+		packs:
+		EOF
+		if test $NUM_PACKS -ge 1
+		then
+			ls $OBJECT_DIR/pack/ | grep idx | sort
+		fi &&
+		printf "object-dir: $OBJECT_DIR\n"
+	} >expect &&
+	test-tool read-midx $OBJECT_DIR >actual &&
+	test_cmp expect actual
+}
+
+test_expect_success 'write midx with no packs' '
+	test_when_finished rm -f pack/multi-pack-index &&
+	git multi-pack-index --object-dir=. write &&
+	midx_read_expect 0 0 4 .
+'
+
+generate_objects () {
+	i=$1
+	iii=$(printf '%03i' $i)
+	{
+		test-tool genrandom "bar" 200 &&
+		test-tool genrandom "baz $iii" 50
+	} >wide_delta_$iii &&
+	{
+		test-tool genrandom "foo"$i 100 &&
+		test-tool genrandom "foo"$(( $i + 1 )) 100 &&
+		test-tool genrandom "foo"$(( $i + 2 )) 100
+	} >deep_delta_$iii &&
+	{
+		echo $iii &&
+		test-tool genrandom "$iii" 8192
+	} >file_$iii &&
+	git update-index --add file_$iii deep_delta_$iii wide_delta_$iii
+}
+
+commit_and_list_objects () {
+	{
+		echo 101 &&
+		test-tool genrandom 100 8192;
+	} >file_101 &&
+	git update-index --add file_101 &&
+	tree=$(git write-tree) &&
+	commit=$(git commit-tree $tree -p HEAD</dev/null) &&
+	{
+		echo $tree &&
+		git ls-tree $tree | sed -e "s/.* \\([0-9a-f]*\\)	.*/\\1/"
+	} >obj-list &&
+	git reset --hard $commit
+}
+
+test_expect_success 'create objects' '
+	test_commit initial &&
+	for i in $(test_seq 1 5)
+	do
+		generate_objects $i
+	done &&
+	commit_and_list_objects
+'
+
+test_expect_success 'write midx with one v1 pack' '
+	pack=$(git pack-objects --index-version=1 $objdir/pack/test <obj-list) &&
+	test_when_finished rm $objdir/pack/test-$pack.pack \
+		$objdir/pack/test-$pack.idx $objdir/pack/multi-pack-index &&
+	git multi-pack-index --object-dir=$objdir write &&
+	midx_read_expect 1 18 4 $objdir
+'
+
+midx_git_two_modes () {
+	git -c core.multiPackIndex=false $1 >expect &&
+	git -c core.multiPackIndex=true $1 >actual &&
+	test_cmp expect actual
+}
+
+compare_results_with_midx () {
+	MSG=$1
+	test_expect_success "check normal git operations: $MSG" '
+		midx_git_two_modes "rev-list --objects --all" &&
+		midx_git_two_modes "log --raw"
+	'
+}
+
+test_expect_success 'write midx with one v2 pack' '
+	git pack-objects --index-version=2,0x40 $objdir/pack/test <obj-list &&
+	git multi-pack-index --object-dir=$objdir write &&
+	midx_read_expect 1 18 4 $objdir
+'
+
+compare_results_with_midx "one v2 pack"
+
+test_expect_success 'add more objects' '
+	for i in $(test_seq 6 10)
+	do
+		generate_objects $i
+	done &&
+	commit_and_list_objects
+'
+
+test_expect_success 'write midx with two packs' '
+	git pack-objects --index-version=1 $objdir/pack/test-2 <obj-list &&
+	git multi-pack-index --object-dir=$objdir write &&
+	midx_read_expect 2 34 4 $objdir
+'
+
+compare_results_with_midx "two packs"
+
+test_expect_success 'add more packs' '
+	for j in $(test_seq 11 20)
+	do
+		generate_objects $j &&
+		commit_and_list_objects &&
+		git pack-objects --index-version=2 $objdir/pack/test-pack <obj-list
+	done
+'
+
+compare_results_with_midx "mixed mode (two packs + extra)"
+
+test_expect_success 'write midx with twelve packs' '
+	git multi-pack-index --object-dir=$objdir write &&
+	midx_read_expect 12 74 4 $objdir
+'
+
+compare_results_with_midx "twelve packs"
+
+test_expect_success 'repack removes multi-pack-index' '
+	test_path_is_file $objdir/pack/multi-pack-index &&
+	git repack -adf &&
+	test_path_is_missing $objdir/pack/multi-pack-index
+'
+
+compare_results_with_midx "after repack"
+
+
+# usage: corrupt_data <file> <pos> [<data>]
+corrupt_data () {
+	file=$1
+	pos=$2
+	data="${3:-\0}"
+	printf "$data" | dd of="$file" bs=1 seek="$pos" conv=notrunc
+}
+
+# Force 64-bit offsets by manipulating the idx file.
+# This makes the IDX file _incorrect_ so be careful to clean up after!
+test_expect_success 'force some 64-bit offsets with pack-objects' '
+	mkdir objects64 &&
+	mkdir objects64/pack &&
+	for i in $(test_seq 1 11)
+	do
+		generate_objects 11
+	done &&
+	commit_and_list_objects &&
+	pack64=$(git pack-objects --index-version=2,0x40 objects64/pack/test-64 <obj-list) &&
+	idx64=objects64/pack/test-64-$pack64.idx &&
+	chmod u+w $idx64 &&
+	corrupt_data $idx64 2999 "\02" &&
+	midx64=$(git multi-pack-index --object-dir=objects64 write) &&
+	midx_read_expect 1 63 5 objects64 " large-offsets"
+'
+
+test_done